Workflow n8n
Scrape Latest 20 TechCrunch Articles
Scrape la page /latest/0 de TechCrunch, extrait les 20 posts (image, titre, URL, date) puis visite chaque article pour récupérer contenu, miniature et métadonnées nettoyées. Tags clés : scraping, techcrunch, html.
Catégorie: scraping · Tags: scraping, techcrunch, html, http❤ 0
Vue d'ensemble du workflow n8n
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"id": "MKGrRFnUuMZMAxNf",
"meta": {
"instanceId": "0b0f5302e78710cf1b1457ee15a129d8e5d83d4e366bd96d14cc37da6693e692"
},
"name": "Scrape Latest 20 TechCrunch Articles",
"tags": [],
"nodes": [
{
"id": "f757df19-a2b0-42c5-b75e-e4af51696059",
"name": "When clicking ‘Test workflow’",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-400,
160
],
"parameters": {},
"typeVersion": 1
},
{
"id": "1311d3be-cf2e-42ca-ae69-8ebfeb71eefb",
"name": "Request Techcrunsh Latest Page",
"type": "n8n-nodes-base.httpRequest",
"position": [
-220,
160
],
"parameters": {
"url": "=https://techcrunch.com/latest/0",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "c7807fdf-3b0b-40f8-b912-214475501861",
"name": "Parse a posts box",
"type": "n8n-nodes-base.html",
"position": [
-40,
160
],
"parameters": {
"options": {},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "box",
"cssSelector": "ul.wp-block-post-template",
"returnValue": "html"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "4f6720e2-32ee-41dd-a369-a05bb06b4441",
"name": "Parse all posts",
"type": "n8n-nodes-base.html",
"position": [
120,
160
],
"parameters": {
"options": {
"trimValues": true
},
"operation": "extractHtmlContent",
"dataPropertyName": "box",
"extractionValues": {
"values": [
{
"key": "posts",
"cssSelector": "li.wp-block-post",
"returnArray": true,
"returnValue": "html"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "2d4f5589-1c27-4fa0-9c64-34d02fb091cf",
"name": "split out the posts",
"type": "n8n-nodes-base.splitOut",
"position": [
300,
160
],
"parameters": {
"options": {},
"fieldToSplitOut": "posts"
},
"typeVersion": 1
},
{
"id": "bf35ac63-554a-4039-9636-78016110f615",
"name": "Parse each post in detail",
"type": "n8n-nodes-base.html",
"position": [
520,
160
],
"parameters": {
"options": {
"trimValues": true
},
"operation": "extractHtmlContent",
"dataPropertyName": "posts",
"extractionValues": {
"values": [
{
"key": "image",
"attribute": "src",
"cssSelector": "img",
"returnValue": "attribute"
},
{
"key": "title",
"cssSelector": "h3.loop-card__title"
},
{
"key": "url",
"attribute": "data-destinationlink",
"cssSelector": "h3>a",
"returnValue": "attribute"
},
{
"key": "created_at",
"attribute": "datetime",
"cssSelector": "time",
"returnValue": "attribute"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "2aedd43b-5c04-410e-be37-7e84b798e551",
"name": "Request a post detail page",
"type": "n8n-nodes-base.httpRequest",
"position": [
720,
160
],
"parameters": {
"url": "={{ $json.url }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "e0d9eb9c-096c-47de-b39a-d72083d403de",
"name": "Parse a post's content and metadata",
"type": "n8n-nodes-base.html",
"position": [
940,
160
],
"parameters": {
"options": {
"trimValues": true,
"cleanUpText": true
},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "content",
"cssSelector": "div.entry-content"
},
{
"key": "title",
"cssSelector": "h1.wp-block-post-title"
},
{
"key": "thumbnail",
"attribute": "src",
"cssSelector": "img.attachment-post-thumbnail",
"returnValue": "attribute"
},
{
"key": "created_at",
"attribute": "datetime",
"cssSelector": "time",
"returnValue": "attribute"
}
]
}
},
"executeOnce": false,
"typeVersion": 1.2
},
{
"id": "513c616e-9362-4246-a420-70c93863ad6e",
"name": "Save the values",
"type": "n8n-nodes-base.set",
"position": [
1120,
160
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "411666fc-c934-4cfe-93c8-dd2ba426fa46",
"name": "url",
"type": "string",
"value": "={{ $('Parse each post in detail').item.json.url }}"
},
{
"id": "251700fe-bfee-46a6-b157-c0d029edb594",
"name": "created_at",
"type": "string",
"value": "={{ $('Parse each post in detail').item.json.created_at }}"
},
{
"id": "296f4201-06a3-4d81-b85f-5d0b045e09bd",
"name": "image",
"type": "string",
"value": "={{ $('Parse each post in detail').item.json.image }}"
},
{
"id": "1af47c5f-1b6e-4894-b7c5-9a037a328a0d",
"name": "content",
"type": "string",
"value": "={{ $json.content }}"
},
{
"id": "5595be9f-7d2a-43c5-8b40-839f787e9ace",
"name": "title",
"type": "string",
"value": "={{ $json.title }}"
}
]
}
},
"typeVersion": 3.4
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "6f14b55f-11a9-46f6-ba96-4abdfd3fe2f8",
"connections": {
"Parse all posts": {
"main": [
[
{
"node": "split out the posts",
"type": "main",
"index": 0
}
]
]
},
"Parse a posts box": {
"main": [
[
{
"node": "Parse all posts",
"type": "main",
"index": 0
}
]
]
},
"split out the posts": {
"main": [
[
{
"node": "Parse each post in detail",
"type": "main",
"index": 0
}
]
]
},
"Parse each post in detail": {
"main": [
[
{
"node": "Request a post detail page",
"type": "main",
"index": 0
}
]
]
},
"Request a post detail page": {
"main": [
[
{
"node": "Parse a post's content and metadata",
"type": "main",
"index": 0
}
]
]
},
"Request Techcrunsh Latest Page": {
"main": [
[
{
"node": "Parse a posts box",
"type": "main",
"index": 0
}
]
]
},
"When clicking ‘Test workflow’": {
"main": [
[
{
"node": "Request Techcrunsh Latest Page",
"type": "main",
"index": 0
}
]
]
},
"Parse a post's content and metadata": {
"main": [
[
{
"node": "Save the values",
"type": "main",
"index": 0
}
]
]
}
}
}